GIS and Geostatistics for Supporting Environmental Analyses in Space-Time

The book aims to investigate methods and techniques for spatial statistical analysis suitable to model spatial information in support of decision systems. Over the last few years there has been a considerable interest in these tools and in the role they can play in spatial planning and environmental modelling. One of the earliest and most famous definition of spatial planning was “a geographical expression to the economic, social, cultural and ecological policies of society”: borrowing from this point of view, this text shows how an interdisciplinary approach is an effective way to an harmonious integration of national policies with regional and local analysis. A wide range of spatial models and techniques is, also, covered: spatial data mining, point processes analysis, nearest neighbor statistics and cluster detection, Fuzzy Regression model and local indicators of spatial association; all of these tools provide the policy-maker with a valuable support to policy development. Chapter 4 Abstract: The environmental risk assessment involves the analysis of complex phenomena. Different kinds of information, such as environmental, socio-economic, political and institutional data, are usually collected. In this chapter, spatio-temporal geostatistical analysis is combined with the use of a Geographic Information System (GIS): the integration between geostatistical tools and GIS enables the identification and the visualization of alternative scenarios regarding a phenomenon under study and supports the environmental risk management. A case study on environmental data measured at different monitoring stations in the southern part of Apulia Region (South of Italy), called Grande Salento, is discussed. Sample data concerning daily averages of PM10, Wind Speed and Atmospheric Temperature, are used for stochastic prediction, through space–time indicator kriging. Kriging results are implemented in a GIS and a 3D representation of the spatio-temporal probability maps is proposed